paper-with-me

홈 › Papers

Scrutinizing the Vulnerability of Decentralized Learning to Membership Inference Attacks

2024-12-17 · Ousmane Touat, Jezekael Brunon, Yacine Belal, Julien Nicolas, Mohamed Maouche, César Sabater, Sonia Ben Mokhtar

The primary promise of decentralized learning is to allow users to engage in the training of machine learning models in a collaborative manner while keeping their data on their premises and without relying on any central entity. However, this paradigm necessitates the exchange of model parameters or gradients between peers. Such exchanges can be exploited to infer sensitive information about training data, which is achieved through privacy attacks (e.g Membership Inference Attacks -- MIA). In order to devise effective defense mechanisms, it is important to understand the factors that increase/reduce the vulnerability of a given decentralized learning architecture to MIA. In this study, we extensively explore the vulnerability to MIA of various decentralized learning architectures by varying the graph structure (e.g number of neighbors), the graph dynamics, and the aggregation strategy, across diverse datasets and data distributions. Our key finding, which to the best of our knowledge we are the first to report, is that the vulnerability to MIA is heavily correlated to (i) the local model mixing strategy performed by each node upon reception of models from neighboring nodes and (ii) the global mixing properties of the communication graph. We illustrate these results experimentally using four datasets and by theoretically analyzing the mixing properties of various decentralized architectures. Our paper draws a set of lessons learned for devising decentralized learning systems that reduce by design the vulnerability to MIA.

📄 PDF Abstract BibTeX arXiv:2412.12837

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation

2024-05-13 · Andrey V. Galichin, Mikhail Pautov, Alexey Zhavoronkin, Oleg Y. Rogov 외

While Deep Neural Networks (DNNs) have demonstrated remarkable performance in tasks related to perception and control, there are still several unresolved concerns regarding the privacy of their training data, particularl…

image-classificationImage ClassificationInference AttackKnowledge Distillation+1

Effects of Differential Privacy and Data Skewness on Membership Inference Vulnerability

2019-11-21 · Stacey Truex, Ling Liu, Mehmet Emre Gursoy, Wenqi Wei 외

Membership inference attacks seek to infer the membership of individual training instances of a privately trained model. This paper presents a membership privacy analysis and evaluation system, called MPLens, with three …

Inference AttackMembership Inference Attack

Securing Genomic Data Against Inference Attacks in Federated Learning Environments

2025-05-12 · Chetan Pathade, Shubham Patil

Federated Learning (FL) offers a promising framework for collaboratively training machine learning models across decentralized genomic datasets without direct data sharing. While this approach preserves data locality, it…

Federated LearningInference AttackMembership Inference AttackPrivacy Preserving

On the Importance of Difficulty Calibration in Membership Inference Attacks

2021-11-15 · ICLR 2022 4 · Lauren Watson, Chuan Guo, Graham Cormode, Alex Sablayrolles

The vulnerability of machine learning models to membership inference attacks has received much attention in recent years. However, existing attacks mostly remain impractical due to having high false positive rates, where…

On the Vulnerability of Data Points under Multiple Membership Inference Attacks and Target Models

2022-10-28 · Mauro Conti, Jiaxin Li, Stjepan Picek

Membership Inference Attacks (MIAs) infer whether a data point is in the training data of a machine learning model. It is a threat while being in the training data is private information of a data point. MIA correctly in…